Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Miao Zhang et al.
Summary: Dealing with intra and inter-modality features is crucial for RGB-D salient object detection. This paper proposes a new model that achieves accurate predictions of salient objects by decoupling dynamic convolution and introducing a criss-cross dynamic filter network.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Xiaolong Cheng et al.
Summary: In this paper, a deep-induced gap-reducing network (DIGR-Net) is proposed for assessing depth quality and enhancing salient object detection. The network utilizes an interpretable mechanism called interference degree (ID) to reweight feature contributions, and incorporates a cross-modality interaction block and mutually guided cross-level fusion module to reduce semantic and intrinsic gaps. A refinement branch is also introduced to enhance salient regions.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Yuzhu Ji et al.
Summary: In this paper, a local-to-global context-aware feature augmentation network (LGCNet) is proposed for salient object detection, utilizing fully convolutional network for pixel-level classification. The LGCNet incorporates a two-branch attention-based context relation modeling structure and a pixel-wise self-attention mechanism to achieve coarse-to-fine detection model, showing promising results on multiple benchmark datasets.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Haishun Du et al.
Summary: Researchers propose a two-level salient feature complementary network (TSFC-Net) for person re-identification, which can extract the most salient discriminative features and the secondary salient discriminative features of pedestrian images. Experimental results show that TSFC-Net outperforms most state-of-the-art methods.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yanhua Liang et al.
Summary: In this paper, a novel end-to-end unified framework is proposed for RGB-D and RGB-T salient object detection. The framework consists of three key components: multi-modal interactive attention unit, joint attention guided cross-modal decoding module, and multi-level feature progressive decoding module. Experimental results show that the proposed method outperforms other state-of-the-art methods and has good generalization.
Proceedings Paper
Computer Science, Artificial Intelligence
Youwei Pang et al.
Summary: The article proposes a mixed-scale triplet network, ZoomNet, that mimics human behavior of zooming in and out to address the challenges in camouflaged object detection. The network learns discriminative mixed-scale semantics through a zoom strategy and introduces an uncertainty-aware loss to improve prediction accuracy.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Tao Zhou et al.
Summary: In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection. The proposed network includes several modules such as the Boundary Guidance Module (BGM), Multi-scale Feature Aggregation Module (MFAM), and Cross-level Fusion and Propagation Module (CFPM), which contribute to improving the performance of camouflaged object detection. Extensive experiments on benchmark datasets demonstrate the superiority of our proposed FAP-Net.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Yi Liu et al.
Summary: The paper introduces a new Multi-Scale Deformation Module (MSDM) and Channel-Wise Attention Mechanism (CWAM) to extract salient objects of varying sizes and shapes, while highlighting informative channels and suppressing confusing channels. Experimental results demonstrate the superiority of the proposed method over state-of-the-art approaches.
Proceedings Paper
Computer Science, Artificial Intelligence
Nian Liu et al.
Summary: This paper proposes a unified model VST based on Transformer for RGB and RGB-D salient object detection, achieving saliency prediction through modeling long-range dependencies and introducing multi-level token fusion and token upsampling methods under the transformer framework. Additionally, a token-based multi-task decoder is developed to perform saliency and boundary detection simultaneously.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xuebin Qin et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhe Wu et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Computer Science, Artificial Intelligence
Wenbin Zou et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Nianyi Li et al.
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2014)
Proceedings Paper
Computer Science, Artificial Intelligence
Ran Margolin et al.
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2014)
Proceedings Paper
Computer Science, Artificial Intelligence
Houwen Peng et al.
COMPUTER VISION - ECCV 2014, PT III
(2014)
Article
Computer Science, Artificial Intelligence
Lining Zhang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2012)